切换至 "中华医学电子期刊资源库"

中华脑血管病杂志(电子版) ›› 2023, Vol. 17 ›› Issue (01) : 26 -30. doi: 10.11817/j.issn.1673-9248.2023.01.005

临床研究

人工智能辅助CT血管成像脑血管重建在基层医院颅内动脉瘤诊断中的应用
付永鹏1, 拉巴索朗1, 马强1, 陈群超1, 郑裕峰2, 吴蕻2, 郑圆杰3, 胡婧3, 于洮4,(), 张东5   
  1. 1. 850000 拉萨,拉萨市人民医院神经外科
    2. 100085 北京,北京智像科技有限公司
    3. 102299 北京,数坤(北京)网络科技股份有限公司
    4. 850000 拉萨,拉萨市人民医院神经外科;100050 北京,首都医科大学附属北京天坛医院,北京市神经外科研究所
    5. 100050 北京,首都医科大学附属北京天坛医院,北京市神经外科研究所
  • 收稿日期:2022-05-25 出版日期:2023-02-01
  • 通信作者: 于洮
  • 基金资助:
    国家重点研发计划(2021YFC2500500); 首都卫生发展科研专项(2022-2-1075); 西藏自治区自然科学基金组团式医学援藏项目(XZ2022ZR-ZY19(Z))

Application of artificial intelligence-assisted vascular reconstruction in diagnosis of intracranial aneurysms in Tibet

Yongpeng Fu1, La ba suo lang1, Qiang Ma1, Qunchao Chen1, Yufeng Zheng2, Hong Wu2, Yuanjie Zheng3, Jing Hu3, Tao Yu4,(), Dong Zhang5   

  1. 1. Department of Neurosurgery, People's Hospital of Lhasa, Lhasa 850000, China
    2. Beijing Telezx Technology Co., Ltd, Beijing 100085, China
    3. Shukun (Beijing) Technology Co., Ltd, Beijing 102299, China
    4. Department of Neurosurgery, People's Hospital of Lhasa, Lhasa 850000, China; Beijing Tiantan Hospital affiliated to Capital Medical University, Beijing Institute of Neurosurgery, 100050 Beijing, China
    5. Beijing Tiantan Hospital affiliated to Capital Medical University, Beijing Institute of Neurosurgery, 100050 Beijing, China
  • Received:2022-05-25 Published:2023-02-01
  • Corresponding author: Tao Yu
引用本文:

付永鹏, 拉巴索朗, 马强, 陈群超, 郑裕峰, 吴蕻, 郑圆杰, 胡婧, 于洮, 张东. 人工智能辅助CT血管成像脑血管重建在基层医院颅内动脉瘤诊断中的应用[J]. 中华脑血管病杂志(电子版), 2023, 17(01): 26-30.

Yongpeng Fu, La ba suo lang, Qiang Ma, Qunchao Chen, Yufeng Zheng, Hong Wu, Yuanjie Zheng, Jing Hu, Tao Yu, Dong Zhang. Application of artificial intelligence-assisted vascular reconstruction in diagnosis of intracranial aneurysms in Tibet[J]. Chinese Journal of Cerebrovascular Diseases(Electronic Edition), 2023, 17(01): 26-30.

目的

探讨人工智能辅助CT血管成像(CTA)在西藏地区颅内动脉瘤诊治中的应用价值。

方法

回顾性分析2021年8月至2022年4月拉萨市人民医院神经外科收治的26例颅内动脉瘤患者。所有患者均于24 h内行CTA检查,数据分别使用人工智能辅助和人工方法进行脑血管三维重建,比较2种方法的重建时间、诊断结果、图像质量。采用独立样本t检验比较人工智能重建组和人工重建组重建时间和图像评分的差异,采用χ2检验比较疾病诊断准确性的差异。

结果

人工智能重建组动脉瘤位置诊断准确性为92.3%(24/26),人工重建组准确性为96.2%(25/26),2组差异无统计学意义(P>0.05)。人工智能重建组CTA重建所需时间显著低于人工重建组[(24.2±11.8)min vs (94.7±42.0)min],差异具有统计学意义(t=-8.82,P<0.001)。人工智能重建组图像评分高于人工重建组[(4.53±0.58)分 vs (3.46±0.94)分],差异具有统计学意义(t=4.24,P<0.001)。

结论

人工智能辅助CTA脑血管重建成像技术较人工重建更快速,显示动脉瘤情况更满意,适合在基层医院应用。

Objective

To investigate the application value of artificial intelligence (AI)-assisted CT angiography (CTA) in diagnosing and treating intracranial aneurysms in Tibet.

Methods

The author retrospectively reviewed 26 patients diagnosed with intracranial aneurysms admitted to the Department of Neurosurgery of Lhasa People's Hospital from October 2021 to April 2022. All patients underwent CTA examination within 24 hours after admission. The data were reconstructed using both AI-assisted and manual methods for 3D reconstruction of cerebral blood vessels, respectively. The variables of reconstruction time, diagnostic accuracy, and image quality between two groups were compared. Independent samples t-test was used for continuous variables, and chi-square test for categorical samples.

Results

The diagnostic accuracy of the aneurysm was 92.3%(24/26) in the AI group and 96.2%(25/26) in the manual group, reaching no significant difference between two groups (P>0.05). The time interval required for CTA reconstruction was 24.2±11.8 minutes in the AI-assisted group, which was significantly lower than 94.7±42.0 minutes in the manual group (t=-8.82, P<0.001). The reconstruction quality score of the AI group was 4.53±0.58, and that of the manual group was 3.46±0.94. The AI group was significantly better than the artificial group (t=4.24, P<0.001).

Conclusion

AI-assisted CTA cerebral vascular reconstruction imaging technology is faster than manual reconstruction, and shows more satisfactory aneurysm condition, which is suitable for promotion in primary hospitals.

图1 CTA图像上传智像AI工作站计算过程示意图 注:CTA为CT血管成像,PACS为影像归档和通信系统,AI为人工智能
表1 人工智能重建组和人工重建组的CT血管成像准确性、重建时间和重建质量比较
图2 CT血管成像颅内血管三维重建对比。CT扫描多平面重建相显示右侧大脑中动脉动脉瘤(图a)。北京远程智像系统人工智能重建(图b)可多方位显示动脉瘤载瘤动脉、血管关系、子瘤等信息。拉萨市人民医院的颅内血管人工重建(图c)显示的动脉瘤层面较少
1
Gathier CS, Dankbaar JW, van der Jagt M, et al. Effects of induced hypertension on cerebral perfusion in delayed cerebral ischemia after aneurysmal subarachnoid hemorrhage: a randomized clinical trial [J]. Stroke, 2015, 46(11): 3277-3281.
2
Macdonald RL, Schweizer TA. Spontaneous subarachnoid haemorrhage [J]. Lancet, 2017, 389(10069): 655-666.
3
Westerlaan HE, van Dijk JM, Jansen-van der Weide MC, et al. Intracranial aneurysms in patients with subarachnoid hemorrhage: CT angiography as a primary examination tool for diagnosis-systematic review and meta-analysis [J]. Radiology, 2011, 258(1): 134-145.
4
Fu F, Wei J, Zhang M, et al. Rapid vessel segmentation and reconstruction of head and neck angiograms using 3D convolutional neural network [J]. Nat Commun, 2020, 11(1): 4829.
5
Boos J, Fang J, Heidinger BH, et al. Dual energy CT angiography: pros and cons of dual-energy metal artifact reduction algorithm in patients after endovascular aortic repair [J]. Abdom Radio (NY), 2017, 42(3): 749-758.
6
康慧斌, 刘爱华, 李佑祥, 等. 影响颅内动脉瘤破裂的临床危险因素分析 [J]. 中华神经外科杂志, 2018, 34(10): 1012-1016.
7
Sun H, Li W, Ma J, et al. CT perfusion diagnoses delayed cerebral ischemia in the early stage of the time-window after aneurysmal subarachnoid hemorrhage [J]. J Neuroradiol, 2017, 44(5): 313-318.
8
Vakil P, Ansari SA, Cantrell CG, et al. Quantifying intracranial aneurysm wall permeability for risk assessment using dynamic contrast-enhanced MRI: a pilot study [J]. AJNR Am J Neuroradiol, 2015, 36(5): 953-959.
9
刘建民. 颅内动脉瘤的血管内治疗——从血管重建到血流重构 [J]. 中华神经外科杂志, 2019, 35(9): 865-867.
10
Saxena A, Eyk N, Lim ST. Imaging modalities to diagnose carotid artery stenosis: progress and prospect [J]. Biomed Eng Online, 2019, 18(1): 66.
[1] 张梅芳, 谭莹, 朱巧珍, 温昕, 袁鹰, 秦越, 郭洪波, 侯伶秀, 黄文兰, 彭桂艳, 李胜利. 早孕期胎儿头臀长正中矢状切面超声图像的人工智能质控研究[J]. 中华医学超声杂志(电子版), 2023, 20(09): 945-950.
[2] 唐玮, 何融泉, 黄素宁. 深度学习在乳腺癌影像诊疗和预后预测中的应用[J]. 中华乳腺病杂志(电子版), 2023, 17(06): 323-328.
[3] 范帅华, 郭伟, 郭军. 基于机器学习的决策树算法在血流感染预后预测中应用现状及展望[J]. 中华实验和临床感染病杂志(电子版), 2023, 17(05): 289-293.
[4] 张辉, 蔡敏, 黄湘雅. 数字化技术和人工智能在上颌窦底提升术的临床应用[J]. 中华口腔医学研究杂志(电子版), 2023, 17(04): 244-252.
[5] 李晓阳, 刘柏隆, 周祥福. 大数据及人工智能对女性盆底功能障碍性疾病的诊断及风险预测[J]. 中华腔镜泌尿外科杂志(电子版), 2023, 17(06): 549-552.
[6] 李腾成, 狄金明. 2023 V1版前列腺癌NCCN指南更新要点解读[J]. 中华腔镜泌尿外科杂志(电子版), 2023, 17(04): 313-318.
[7] 邢晓伟, 刘雨辰, 赵冰, 王明刚. 基于术前腹部CT的卷积神经网络对腹壁切口疝术后复发预测价值[J]. 中华疝和腹壁外科杂志(电子版), 2023, 17(06): 677-681.
[8] 韩冰, 顾劲扬. 深度学习神经网络在肝癌诊疗中的研究及应用前景[J]. 中华肝脏外科手术学电子杂志, 2023, 12(05): 480-485.
[9] 雷漫诗, 邓锶锶, 汪昕蓉, 黄锦彬, 向青, 熊安妮, 孟占鳌. 人工智能辅助压缩感知技术在上腹部T2WI压脂序列中的应用[J]. 中华肝脏外科手术学电子杂志, 2023, 12(05): 551-556.
[10] 王晓东, 汪恺, 葛昭, 丁忠祥, 徐骁. 计算机视觉技术在肝癌肝移植疗效提升中的研究进展[J]. 中华肝脏外科手术学电子杂志, 2023, 12(04): 361-366.
[11] 葛云鹏, 崔红元, 宋京海. 人工智能在原发性肝癌诊断、治疗及预后中的应用[J]. 中华肝脏外科手术学电子杂志, 2023, 12(04): 367-371.
[12] 李京珂, 张妍春, 武佳懿, 任秀瑜. 深度学习在糖尿病视网膜病变筛查、评级及管理中的研究进展[J]. 中华眼科医学杂志(电子版), 2023, 13(04): 241-246.
[13] 朱泽超, 杨新宇, 李侑埕, 潘鹏宇, 梁国标. 染料木黄酮通过SIRT1/p53信号通路对蛛网膜下腔出血后早期脑损伤的作用[J]. 中华神经创伤外科电子杂志, 2023, 09(05): 261-269.
[14] 李秦鹏, 王其涛, 朱媛媛, 周琦, 刘笑言, 许勇. 颈动脉彩色多普勒超声、颈部CT血管成像及脑部CT灌注成像在脑梗死并发颈动脉狭窄患者中的应用研究[J]. 中华脑血管病杂志(电子版), 2023, 17(05): 482-488.
[15] 胡平, 鄢腾峰, 周海柱, 祝新根. 人工智能在非增强CT图像中颅内出血早期检出和血肿分割的研究进展[J]. 中华脑血管病杂志(电子版), 2023, 17(04): 410-416.
阅读次数
全文


摘要